A methodology to explain neural network classification

By Raphaël Féraud, Fabrice Clérot. 2002

158 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Computer Vision and Pattern Recognition

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “…2017; Donahue, et al., 2015; Doshi-Velez and Kim, 2017; Elenberg, Dimakis, Feldman, and Karbasi, 2017; Erhan, Bengio, Courville, and Vincent, 2009; Féraud and Clérot, 2002; Fukui et al., 2016; Gan, Wang, Yang, Yeung, and Hauptmann, 2015; Goyal, et al., 2016a,b,c; Hendricks et al., 2016; Hinton,…”
How to Explain Individual Classification Decisions (2009, background): “For multi-layer perceptrons F´eraud and Cl´erot (2002) measure the importance of individual input variables on clusters of test points.”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “Feature Importance [163] and Feature Perturbation [164] are also based on algorithms that modify subsets of the input features to find groups of interacting attributes used by different classifiers and to determine the extent to which a model exploits such interactions.”
Building credit scoring models using genetic programming (2005, methodology): “Although many methods have been proposed to deal with the problem of variable selection (Feraud & Cleror, 2002; Nath et al., 1997), it is time waste and makes the model more complicated.”
Explanation and Justification in Machine Learning : A Survey Or (2017, background): “Such proposals were made for Bayesian networks [Suermondt, 1992], multi-layer Perceptrons [Feraud and Clerot, 2002], RBF networks [Robnik-ˇSikonja et al. , 2011] and general hierarchical networks [Landecker et al. , 2013].”